Web projektu DAR

Výzkumné centrum
Data - Algoritmy - Rozhodování

Založeno v roce 2005 s podporou MŠMT ČR (projekt 1M0572)

Publikace

Goodness-of-fit Testing Based on Hypothetical and Empirical Quantizations.

Typ:

Interní tisk

Autoři publikace:

Vajda I., van der Meulen E.C.

Název edice / řada:

Interní publikace DAR -

Svazek:

ÚTIA 2006/14

Nakladatel:

ÚTIA AV ČR

Místo vydání:

Praha

Rok:

2006

Počet stran:

Kontaktní osoba:

Ing. Igor Vajda, DrSc. (ÚTIA - Oddělení stochastické informatiky)

Klíčová slova:

Goodness-of-fit, Spacings, phi-divergence, power divergence

příloha1:

Goodness-of-fit Testing Based on Hypothetical and Empirical Quantizations. [file]

Anotace:

Revised and updated version of the Research Report UTIA no. 2160. Pearson-type statistics are demonstrated to be special cases of pfi-divergences of hypothetical and empirical distributions quantized by hypothetical quantiles. New class of spacing statistics is introduced by means of empirical quantiles. General asymptotic theory of the new statistics is presented and applied to their subclass generated by the power divergences. Concrete examples and calculated values are presented in the form of tables.